Image Segmentation of MRI Images using KMCG and KFCG Algorithms

Segmentation of medical images is very important nowadays since the images for diagnosis by Radiologist are huge in number. In this paper, texture based segmentation algorithms are considered for comparison. The problem with some of these methods is, they need human interaction for accurate and reliable segmentation. Segmentation based on Gray level co-occurrence matrix gives better result for variance but computational complexity is more. Watershed has less complexity but gives over segmentation. Segmentation using Kekre’s Median Codebook Generation (KMCG) and Kekre’s Fast Codebook Generation (KFCG) algorithm show proper tumor demarcation by avoiding other part of the image.